%0 Journal Article
%T A Highly Reliable Reconstruction of a BP Network When Input Errors Considered<br>考虑输入错误时一个BP网络的高可靠重构
%A Yao Zengqi
%A <br>姚增起
%J 自动化学报
%D 1992
%I 
%X The input errors of BP(Back-Propagation) network are classified into dead point error and phase reversal error in this paper. A highly reliable reconstruction method for a BP network is proposed. The reliability problem of the reconstructed BP network is discussed under the above mentioned input errors respectively. It is shown that, when the probabilities that the inputs are correct (input reliabilities) are varying within a determined region, by increasing the number of inputs, the probability that the reconstructed BP network realizes the giyen function correctly (network reliability) may approach 1. The reconstructed BP network is fault tolerant to input errors to some extent.
%K BP network
%K input errors
%K dead point error
%K phase reversal error
%K reconstruction<br>神经网络
%K BP网络
%K 可靠度
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=E76622685B64B2AA896A7F777B64EB3A&aid=D62FF78B8F2702B5C64C39ADB78A281A&yid=F53A2717BDB04D52&vid=13553B2D12F347E8&iid=94C357A881DFC066&sid=CEFF71AEB051114C&eid=C7A2B92569DF5458&journal_id=0254-4156&journal_name=自动化学报&referenced_num=0&reference_num=2